© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3378
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -Identifier
    -0.26
    )prepare
    -0.22
     sez
    -0.22
    (DBG
    -0.22
    almart
    -0.20
    GetSize
    -0.20
     =>$
    -0.20
     TMPro
    -0.19
    atur
    -0.19
    -Headers
    -0.19
    POSITIVE LOGITS
    ().'/
    0.22
    çIJ¬
    0.21
     subpo
    0.21
    èħ©
    0.20
    ':''
    0.19
    âľķ
    0.19
    asInstanceOf
    0.19
    <![
    0.19
    éŃij
    0.19
    tons
    0.19
    Activations Density 0.109%

    No Known Activations